Skip to content

The project involves parallelizing the construction of suffix arrays on the GPU for the purpose of genome indexing.

Notifications You must be signed in to change notification settings

ajnarayan/Genome-indexing-on-GPU

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

46 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Genome Indexing on the GPU

Construction of suffix arrays on the GPU using CUDA.

<last edit: 05/14/12>

Parallel quick sort

bucketsort/qsort.cu - Parallel bucket sort + Parallel quick sort of suffix array.

Compile using

nvcc -I <NVIDIA_SDK_PATH>/C/common/inc qsort.cu -o qsort

Run as

./qsort <suffix_size, multiple of 1024> <genome_file>

e.g. ./qsort 10240 genome

bucketsort/bsort.cu - Parallel Bucket sort based on common prefix.

Thrust sort

sort.cu - Program to sort the suffixes of a string on the GPU using the thrust libraries and CUDA.

DC3 algorithm

dc3.c - Linear time suffix array consruction on the CPU

Quick sort CPU

quick_sort.c - A program to sort suffixes of a string using quick sort on CPU.

Time Complexity: O(n^2*log(n))

Authors

Varrun Ramani vramani@cs.stonybrook.edu

Shishir Horane shorane@cs.stonybrook.edu

Ashish Bagate abagate@cs.stonybrook.edu

About

The project involves parallelizing the construction of suffix arrays on the GPU for the purpose of genome indexing.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Cuda 84.4%
  • C 13.6%
  • Other 2.0%